Neural Harmonic-plus-Noise Waveform Model with Trainable Maximum Voice Frequency for Text-to-Speech Synthesis

Neural source-filter (NSF) models are deep neural networks that produce waveforms given input acoustic features. They use dilated-convolution-based neural filter modules to filter sine-based excitation for waveform generation, which is different from WaveNet and flow-based models. One of the NSF models, called harmonic-plus-noise NSF (h-NSF) model, uses separate pairs of source and neural filters to generate harmonic and noise waveform components. It is close to WaveNet in terms of speech quality while being superior in generation speed. The h-NSF model can be improved even further. While h-NSF merges the harmonic and noise components using pre-defined digital low- and high-pass filters, it is well known that the maximum voice frequency (MVF) that separates the periodic and aperiodic spectral bands are time-variant. Therefore, we propose a new h-NSF model with time-variant and trainable MVF. We parameterize the digital low- and high-pass filters as windowed-sinc filters and predict their cut-off frequency (i.e., MVF) from the input acoustic features. Our experiments demonstrated that the new model can predict a good trajectory of the MVF and produce high-quality speech for a text-to-speech synthesis system.

神经源 - 滤波器（NSF）模型是一种深度神经网络，它在给定输入声学特征的情况下生成波形。它们使用基于扩张卷积的神经滤波器模块对基于正弦的激励进行滤波以生成波形，这与WaveNet和基于流的模型不同。其中一种NSF模型，称为谐波加噪声NSF（h - NSF）模型，使用独立的源滤波器和神经滤波器对来生成谐波和噪声波形成分。它在语音质量方面与WaveNet相近，但在生成速度上更优。h - NSF模型还可以进一步改进。虽然h - NSF使用预定义的数字低通和高通滤波器合并谐波和噪声成分，但众所周知，区分周期和非周期频谱带的最大语音频率（MVF）是时变的。因此，我们提出一种具有时变且可训练的MVF的新型h - NSF模型。我们将数字低通和高通滤波器参数化为加窗辛格滤波器，并根据输入声学特征预测它们的截止频率（即MVF）。我们的实验表明，新模型能够预测出良好的MVF轨迹，并为文本到语音合成系统生成高质量的语音。